Study mode - Hackdot

Re:Study mode by teleforce on Tuesday July 29, 2025 @08:34PM (#44729840)

Please check this excellent LLM-RAG AI-driven course assistant at UIUC for an example of university course [1]. It provide citations and references mainly for the course notes so the students can verify the answers and further study the course materials.

[1] AI-driven chat assistant for ECE 120 course at UIUC (only 1 comment by the website creator):

https://news.ycombinator.com/item?id=41431164

[ Parent | on HN ]

Re:Study mode by ink_13 on Tuesday July 29, 2025 @11:11PM (#44730614)

Given the propensity of LLMs to hallucinate references, I'm not sure that really solves anything

[ Parent | on HN ]

Re:Study mode by ok123456 on Wednesday July 30, 2025 @12:39AM (#44730951)

RAG means it injects the source material in and knows the hash of it and can link you right to the source document.

[ Parent | on HN ]

Re:Study mode by PaulRobinson on Wednesday July 30, 2025 @02:00AM (#44731243)

I've worked on systems where we get clickable links to source documents also added to the RAG store.

It is perfectly possible to use LLMs to provide accurate context. It's just asking a SaaS product to do that purely on data it was trained on, is not how to do that.

[ Parent | on HN ]

Re:Study mode by mvieira38 on Wednesday July 30, 2025 @09:42AM (#44734087)

I haven't seen it happen at all with RAG systems. I've built one too at work to search internal stuff, and it's pretty easy to make it spit out accurate references with hyperlinks

[ Parent | on HN ]